© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 2228
    Prev
    Next
    INDEX
    Explanations

    blonde descriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    田村
    -0.69
     모
    -0.69
    dades
    -0.68
     فلزی
    -0.68
    Hoa
    -0.66
    écou
    -0.66
     iron
    -0.65
     Zugang
    -0.65
     Cope
    -0.63
    niana
    -0.63
    POSITIVE LOGITS
    ⌡
    0.77
     compilation
    0.76
    leftrightarrow
    0.75
     arctic
    0.73
     deps
    0.71
     sulf
    0.70
     Meier
    0.70
     Shorts
    0.69
     MBS
    0.69
    StateException
    0.68
    Activations Density 0.064%

    No Known Activations